11 accepted papers
The zero-shot text-to-speech (TTS) method, based on speaker embeddings extracted from reference speech using self-supervised learning (SSL) speech representations, can reproduce speaker characteristics very accurately. However, this approach suffers from degradation in speech synthesis quality when…
We propose StyleCap, a method to generate natural language descriptions of speaking styles appearing in speech. Although most of conventional techniques for para-/non-linguistic information recognition focus on the category classification or the intensity estimation of pre-defined labels, they canno…
Self-supervised learning (SSL) has attracted increased attention for learning meaningful speech representations. Speech SSL models, such as WavLM, employ masked prediction training to encode general-purpose representations. In contrast, speaker SSL models, exemplified by DINO-based models, adopt utt…
This work proposes an advanced text-predicting style embedding for expressive speech synthesis. Text-predicting global style token (TPGST) predicts style embedding from text instead of reference speech and uses it to condition a text-to-speech synthesis (TTS) model, resulting in style TTS without re…
This paper proposes a high-speed neural vocoder for CPU implementation. Two approaches for speeding up autoregressive neural vocoders have been proposed, 1) simultaneous multiple sample generation and 2) subband signal-based vocoder; so far they have been employed independently. Our neural vocoder i…
Recurrent neural network-transducer (RNN-T) is promising for building time-synchronous end-to-end automatic speech recognition (ASR) systems, in part because it does not need frame-wise alignment between input features and target labels in the training step. Although training without alignment is be…
This paper presents a novel speech emotion recognition scheme that can deal with the individuality of emotion perception. Most conventional methods directly model the majority decision of multiple listener’s perceived emotions. However, emotion perception varies with the listener, which means the co…
This paper describes neural ConfNet classification, a novel fully neural network based spoken utterance classification method that uses word confusion networks (ConfNets). Our motivation is to establish a spoken utterance classification method that can precisely understand natural language and robus…
This paper proposes novel frameworks for non-parallel voice conversion (VC) using variational autoencoders (VAEs). Although conventional VAE-based VC models can be trained using non-parallel speech corpora with given speaker representations, phonetic contents of the converted speech tend to vanish b…
This paper presents a novel emotion classification method for natural speech. One of the problems in the state-of-the-art method based on Deep Neural Network (DNN) is the paucity of the training data compared to model complexity. To solve this problem, this paper utilizes the ambiguous emotional utt…
We propose a postfilter based on a generative adversarial network (GAN) to compensate for the differences between natural speech and speech synthesized by statistical parametric speech synthesis. In particular, we focus on the differences caused by over-smoothing, which makes the sounds muffled. Ove…